Backend Engineer for Inference Optimization

Cohere is looking for a Backend Engineer to specialize in optimizing model inference systems. In this remote-first role, you will create low-latency serving infrastructure for advanced backend services.

Candidates for this position must have over five years of backend engineering experience and strong programming skills in Go, Rust, or C++. You'll work on building backend services that enhance Cohere's enterprise API, focusing on batching strategies and performance optimization.

Key Responsibilities:

• • Establish low-latency serving infrastructure for model inference
• • Develop backend services for the enterprise-level API
• • Implement batching strategies to maximize throughput efficiency
• • Optimize model serving and inference processes
• • Collaborate within a remote-first culture

Requirements:

• • 5+ years of relevant backend engineering experience
• • Proficiency in Go, Rust, or C++
• • Experience with low-latency and high-throughput systems
• • Knowledge of model serving optimization
• • Familiarity with gRPC, REST APIs, and microservices
• Utilize your expertise in backend engineering to drive innovations in model inference at Cohere.